© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118484
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in" along with its context related to locations or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mobil
    -0.07
    ovice
    -0.07
    owards
    -0.06
     seria
    -0.06
    缸
    -0.06
    .springboot
    -0.06
     Jeffrey
    -0.06
    bout
    -0.06
    íľ´
    -0.05
     mobil
    -0.05
    POSITIVE LOGITS
     effort
    0.09
    istrovstvÃŃ
    0.08
    dorf
    0.07
    รà¸Ķ
    0.07
    Sharper
    0.07
    letic
    0.07
    islav
    0.06
     rang
    0.06
    overn
    0.06
     offen
    0.06
    Activations Density 0.028%

    No Known Activations